git/t/helper/test-run-command.c
Ævar Arnfjörð Bjarmason fd3aaf53f7 run-command: add an "ungroup" option to run_process_parallel()
Extend the parallel execution API added in c553c72eed (run-command:
add an asynchronous parallel child processor, 2015-12-15) to support a
mode where the stdout and stderr of the processes isn't captured and
output in a deterministic order, instead we'll leave it to the kernel
and stdio to sort it out.

This gives the API same functionality as GNU parallel's --ungroup
option. As we'll see in a subsequent commit the main reason to want
this is to support stdout and stderr being connected to the TTY in the
case of jobs=1, demonstrated here with GNU parallel:

	$ parallel --ungroup 'test -t {} && echo TTY || echo NTTY' ::: 1 2
	TTY
	TTY
	$ parallel 'test -t {} && echo TTY || echo NTTY' ::: 1 2
	NTTY
	NTTY

Another is as GNU parallel's documentation notes a potential for
optimization. As demonstrated in next commit our results with "git
hook run" will be similar, but generally speaking this shows that if
you want to run processes in parallel where the exact order isn't
important this can be a lot faster:

	$ hyperfine -r 3 -L o ,--ungroup 'parallel {o} seq ::: 10000000 >/dev/null '
	Benchmark 1: parallel  seq ::: 10000000 >/dev/null
	  Time (mean ± σ):     220.2 ms ±   9.3 ms    [User: 124.9 ms, System: 96.1 ms]
	  Range (min … max):   212.3 ms … 230.5 ms    3 runs

	Benchmark 2: parallel --ungroup seq ::: 10000000 >/dev/null
	  Time (mean ± σ):     154.7 ms ±   0.9 ms    [User: 136.2 ms, System: 25.1 ms]
	  Range (min … max):   153.9 ms … 155.7 ms    3 runs

	Summary
	  'parallel --ungroup seq ::: 10000000 >/dev/null ' ran
	    1.42 ± 0.06 times faster than 'parallel  seq ::: 10000000 >/dev/null '

A large part of the juggling in the API is to make the API safer for
its maintenance and consumers alike.

For the maintenance of the API we e.g. avoid malloc()-ing the
"pp->pfd", ensuring that SANITIZE=address and other similar tools will
catch any unexpected misuse.

For API consumers we take pains to never pass the non-NULL "out"
buffer to an API user that provided the "ungroup" option. The
resulting code in t/helper/test-run-command.c isn't typical of such a
user, i.e. they'd typically use one mode or the other, and would know
whether they'd provided "ungroup" or not.

We could also avoid the strbuf_init() for "buffered_output" by having
"struct parallel_processes" use a static PARALLEL_PROCESSES_INIT
initializer, but let's leave that cleanup for later.

Using a global "run_processes_parallel_ungroup" variable to enable
this option is rather nasty, but is being done here to produce as
minimal of a change as possible for a subsequent regression fix. This
change is extracted from a larger initial version[1] which ends up
with a better end-state for the API, but in doing so needed to modify
all existing callers of the API. Let's defer that for now, and
narrowly focus on what we need for fixing the regression in the
subsequent commit.

It's safe to do this with a global variable because:

 A) hook.c is the only user of it that sets it to non-zero, and before
    we'll get any other API users we'll refactor away this method of
    passing in the option, i.e. re-roll [1].

 B) Even if hook.c wasn't the only user we don't have callers of this
    API that concurrently invoke this parallel process starting API
    itself in parallel.

As noted above "A" && "B" are rather nasty, and we don't want to live
with those caveats long-term, but for now they should be an acceptable
compromise.

1. https://lore.kernel.org/git/cover-v2-0.8-00000000000-20220518T195858Z-avarab@gmail.com/

Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2022-06-07 10:01:41 -07:00

445 lines
10 KiB
C

/*
* test-run-command.c: test run command API.
*
* (C) 2009 Ilari Liusvaara <ilari.liusvaara@elisanet.fi>
*
* This code is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#include "test-tool.h"
#include "git-compat-util.h"
#include "cache.h"
#include "run-command.h"
#include "strvec.h"
#include "strbuf.h"
#include "parse-options.h"
#include "string-list.h"
#include "thread-utils.h"
#include "wildmatch.h"
#include "gettext.h"
static int number_callbacks;
static int parallel_next(struct child_process *cp,
struct strbuf *err,
void *cb,
void **task_cb)
{
struct child_process *d = cb;
if (number_callbacks >= 4)
return 0;
strvec_pushv(&cp->args, d->args.v);
if (err)
strbuf_addstr(err, "preloaded output of a child\n");
else
fprintf(stderr, "preloaded output of a child\n");
number_callbacks++;
return 1;
}
static int no_job(struct child_process *cp,
struct strbuf *err,
void *cb,
void **task_cb)
{
if (err)
strbuf_addstr(err, "no further jobs available\n");
else
fprintf(stderr, "no further jobs available\n");
return 0;
}
static int task_finished(int result,
struct strbuf *err,
void *pp_cb,
void *pp_task_cb)
{
if (err)
strbuf_addstr(err, "asking for a quick stop\n");
else
fprintf(stderr, "asking for a quick stop\n");
return 1;
}
struct testsuite {
struct string_list tests, failed;
int next;
int quiet, immediate, verbose, verbose_log, trace, write_junit_xml;
};
#define TESTSUITE_INIT { \
.tests = STRING_LIST_INIT_DUP, \
.failed = STRING_LIST_INIT_DUP, \
}
static int next_test(struct child_process *cp, struct strbuf *err, void *cb,
void **task_cb)
{
struct testsuite *suite = cb;
const char *test;
if (suite->next >= suite->tests.nr)
return 0;
test = suite->tests.items[suite->next++].string;
strvec_pushl(&cp->args, "sh", test, NULL);
if (suite->quiet)
strvec_push(&cp->args, "--quiet");
if (suite->immediate)
strvec_push(&cp->args, "-i");
if (suite->verbose)
strvec_push(&cp->args, "-v");
if (suite->verbose_log)
strvec_push(&cp->args, "-V");
if (suite->trace)
strvec_push(&cp->args, "-x");
if (suite->write_junit_xml)
strvec_push(&cp->args, "--write-junit-xml");
strbuf_addf(err, "Output of '%s':\n", test);
*task_cb = (void *)test;
return 1;
}
static int test_finished(int result, struct strbuf *err, void *cb,
void *task_cb)
{
struct testsuite *suite = cb;
const char *name = (const char *)task_cb;
if (result)
string_list_append(&suite->failed, name);
strbuf_addf(err, "%s: '%s'\n", result ? "FAIL" : "SUCCESS", name);
return 0;
}
static int test_failed(struct strbuf *out, void *cb, void *task_cb)
{
struct testsuite *suite = cb;
const char *name = (const char *)task_cb;
string_list_append(&suite->failed, name);
strbuf_addf(out, "FAILED TO START: '%s'\n", name);
return 0;
}
static const char * const testsuite_usage[] = {
"test-run-command testsuite [<options>] [<pattern>...]",
NULL
};
static int testsuite(int argc, const char **argv)
{
struct testsuite suite = TESTSUITE_INIT;
int max_jobs = 1, i, ret;
DIR *dir;
struct dirent *d;
struct option options[] = {
OPT_BOOL('i', "immediate", &suite.immediate,
"stop at first failed test case(s)"),
OPT_INTEGER('j', "jobs", &max_jobs, "run <N> jobs in parallel"),
OPT_BOOL('q', "quiet", &suite.quiet, "be terse"),
OPT_BOOL('v', "verbose", &suite.verbose, "be verbose"),
OPT_BOOL('V', "verbose-log", &suite.verbose_log,
"be verbose, redirected to a file"),
OPT_BOOL('x', "trace", &suite.trace, "trace shell commands"),
OPT_BOOL(0, "write-junit-xml", &suite.write_junit_xml,
"write JUnit-style XML files"),
OPT_END()
};
argc = parse_options(argc, argv, NULL, options,
testsuite_usage, PARSE_OPT_STOP_AT_NON_OPTION);
if (max_jobs <= 0)
max_jobs = online_cpus();
dir = opendir(".");
if (!dir)
die("Could not open the current directory");
while ((d = readdir(dir))) {
const char *p = d->d_name;
if (*p != 't' || !isdigit(p[1]) || !isdigit(p[2]) ||
!isdigit(p[3]) || !isdigit(p[4]) || p[5] != '-' ||
!ends_with(p, ".sh"))
continue;
/* No pattern: match all */
if (!argc) {
string_list_append(&suite.tests, p);
continue;
}
for (i = 0; i < argc; i++)
if (!wildmatch(argv[i], p, 0)) {
string_list_append(&suite.tests, p);
break;
}
}
closedir(dir);
if (!suite.tests.nr)
die("No tests match!");
if (max_jobs > suite.tests.nr)
max_jobs = suite.tests.nr;
fprintf(stderr, "Running %"PRIuMAX" tests (%d at a time)\n",
(uintmax_t)suite.tests.nr, max_jobs);
ret = run_processes_parallel(max_jobs, next_test, test_failed,
test_finished, &suite);
if (suite.failed.nr > 0) {
ret = 1;
fprintf(stderr, "%"PRIuMAX" tests failed:\n\n",
(uintmax_t)suite.failed.nr);
for (i = 0; i < suite.failed.nr; i++)
fprintf(stderr, "\t%s\n", suite.failed.items[i].string);
}
string_list_clear(&suite.tests, 0);
string_list_clear(&suite.failed, 0);
return !!ret;
}
static uint64_t my_random_next = 1234;
static uint64_t my_random(void)
{
uint64_t res = my_random_next;
my_random_next = my_random_next * 1103515245 + 12345;
return res;
}
static int quote_stress_test(int argc, const char **argv)
{
/*
* We are running a quote-stress test.
* spawn a subprocess that runs quote-stress with a
* special option that echoes back the arguments that
* were passed in.
*/
char special[] = ".?*\\^_\"'`{}()[]<>@~&+:;$%"; // \t\r\n\a";
int i, j, k, trials = 100, skip = 0, msys2 = 0;
struct strbuf out = STRBUF_INIT;
struct strvec args = STRVEC_INIT;
struct option options[] = {
OPT_INTEGER('n', "trials", &trials, "number of trials"),
OPT_INTEGER('s', "skip", &skip, "skip <n> trials"),
OPT_BOOL('m', "msys2", &msys2, "test quoting for MSYS2's sh"),
OPT_END()
};
const char * const usage[] = {
"test-tool run-command quote-stress-test <options>",
NULL
};
argc = parse_options(argc, argv, NULL, options, usage, 0);
setenv("MSYS_NO_PATHCONV", "1", 0);
for (i = 0; i < trials; i++) {
struct child_process cp = CHILD_PROCESS_INIT;
size_t arg_count, arg_offset;
int ret = 0;
strvec_clear(&args);
if (msys2)
strvec_pushl(&args, "sh", "-c",
"printf %s\\\\0 \"$@\"", "skip", NULL);
else
strvec_pushl(&args, "test-tool", "run-command",
"quote-echo", NULL);
arg_offset = args.nr;
if (argc > 0) {
trials = 1;
arg_count = argc;
for (j = 0; j < arg_count; j++)
strvec_push(&args, argv[j]);
} else {
arg_count = 1 + (my_random() % 5);
for (j = 0; j < arg_count; j++) {
char buf[20];
size_t min_len = 1;
size_t arg_len = min_len +
(my_random() % (ARRAY_SIZE(buf) - min_len));
for (k = 0; k < arg_len; k++)
buf[k] = special[my_random() %
ARRAY_SIZE(special)];
buf[arg_len] = '\0';
strvec_push(&args, buf);
}
}
if (i < skip)
continue;
strvec_pushv(&cp.args, args.v);
strbuf_reset(&out);
if (pipe_command(&cp, NULL, 0, &out, 0, NULL, 0) < 0)
return error("Failed to spawn child process");
for (j = 0, k = 0; j < arg_count; j++) {
const char *arg = args.v[j + arg_offset];
if (strcmp(arg, out.buf + k))
ret = error("incorrectly quoted arg: '%s', "
"echoed back as '%s'",
arg, out.buf + k);
k += strlen(out.buf + k) + 1;
}
if (k != out.len)
ret = error("got %d bytes, but consumed only %d",
(int)out.len, (int)k);
if (ret) {
fprintf(stderr, "Trial #%d failed. Arguments:\n", i);
for (j = 0; j < arg_count; j++)
fprintf(stderr, "arg #%d: '%s'\n",
(int)j, args.v[j + arg_offset]);
strbuf_release(&out);
strvec_clear(&args);
return ret;
}
if (i && (i % 100) == 0)
fprintf(stderr, "Trials completed: %d\n", (int)i);
}
strbuf_release(&out);
strvec_clear(&args);
return 0;
}
static int quote_echo(int argc, const char **argv)
{
while (argc > 1) {
fwrite(argv[1], strlen(argv[1]), 1, stdout);
fputc('\0', stdout);
argv++;
argc--;
}
return 0;
}
static int inherit_handle(const char *argv0)
{
struct child_process cp = CHILD_PROCESS_INIT;
char path[PATH_MAX];
int tmp;
/* First, open an inheritable handle */
xsnprintf(path, sizeof(path), "out-XXXXXX");
tmp = xmkstemp(path);
strvec_pushl(&cp.args,
"test-tool", argv0, "inherited-handle-child", NULL);
cp.in = -1;
cp.no_stdout = cp.no_stderr = 1;
if (start_command(&cp) < 0)
die("Could not start child process");
/* Then close it, and try to delete it. */
close(tmp);
if (unlink(path))
die("Could not delete '%s'", path);
if (close(cp.in) < 0 || finish_command(&cp) < 0)
die("Child did not finish");
return 0;
}
static int inherit_handle_child(void)
{
struct strbuf buf = STRBUF_INIT;
if (strbuf_read(&buf, 0, 0) < 0)
die("Could not read stdin");
printf("Received %s\n", buf.buf);
strbuf_release(&buf);
return 0;
}
int cmd__run_command(int argc, const char **argv)
{
struct child_process proc = CHILD_PROCESS_INIT;
int jobs;
if (argc > 1 && !strcmp(argv[1], "testsuite"))
exit(testsuite(argc - 1, argv + 1));
if (!strcmp(argv[1], "inherited-handle"))
exit(inherit_handle(argv[0]));
if (!strcmp(argv[1], "inherited-handle-child"))
exit(inherit_handle_child());
if (argc >= 2 && !strcmp(argv[1], "quote-stress-test"))
return !!quote_stress_test(argc - 1, argv + 1);
if (argc >= 2 && !strcmp(argv[1], "quote-echo"))
return !!quote_echo(argc - 1, argv + 1);
if (argc < 3)
return 1;
while (!strcmp(argv[1], "env")) {
if (!argv[2])
die("env specifier without a value");
strvec_push(&proc.env_array, argv[2]);
argv += 2;
argc -= 2;
}
if (argc < 3)
return 1;
strvec_pushv(&proc.args, (const char **)argv + 2);
if (!strcmp(argv[1], "start-command-ENOENT")) {
if (start_command(&proc) < 0 && errno == ENOENT)
return 0;
fprintf(stderr, "FAIL %s\n", argv[1]);
return 1;
}
if (!strcmp(argv[1], "run-command"))
exit(run_command(&proc));
if (!strcmp(argv[1], "--ungroup")) {
argv += 1;
argc -= 1;
run_processes_parallel_ungroup = 1;
}
jobs = atoi(argv[2]);
strvec_clear(&proc.args);
strvec_pushv(&proc.args, (const char **)argv + 3);
if (!strcmp(argv[1], "run-command-parallel"))
exit(run_processes_parallel(jobs, parallel_next,
NULL, NULL, &proc));
if (!strcmp(argv[1], "run-command-abort"))
exit(run_processes_parallel(jobs, parallel_next,
NULL, task_finished, &proc));
if (!strcmp(argv[1], "run-command-no-jobs"))
exit(run_processes_parallel(jobs, no_job,
NULL, task_finished, &proc));
fprintf(stderr, "check usage\n");
return 1;
}